© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11786
    Prev
    Next
    INDEX
    Explanations

    the word "external" and related concepts like "internal" and "introduced".

    oai_token-act-pair · gemini-2.0-flash

    external

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parcelize
    -0.49
     automatico
    -0.48
     للاسماء
    -0.46
    PerformLayout
    -0.46
     îna
    -0.43
     velikost
    -0.42
     otomatis
    -0.41
     récupération
    -0.41
     mediodía
    -0.41
    glfw
    -0.40
    POSITIVE LOGITS
    isations
    0.70
    RenderAtEndOf
    0.62
    isation
    0.60
     CommandType
    0.60
    izations
    0.59
     Audiodateien
    0.59
    ismic
    0.59
    omod
    0.58
     TAMBÉM
    0.57
     kasarigan
    0.56
    Activations Density 1.718%

    No Known Activations